© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47698
    Prev
    Next
    INDEX
    Explanations

    Aqua/Ra

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     circumstance
    -0.08
     условия
    -0.08
    次数
    -0.07
    な
    -0.07
    RW
    -0.07
    222
    -0.07
     deeds
    -0.07
    �
    -0.07
     replacement
    -0.07
     grace
    -0.07
    POSITIVE LOGITS
     ску
    0.09
     प्रतिभ
    0.09
     جانب
    0.09
     ดาว
    0.08
     شخصیت
    0.08
     կազմ
    0.08
    ებას
    0.08
     Sleep
    0.08
    ավորմ
    0.08
     აგ
    0.08
    Activations Density 0.000%

    No Known Activations